Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130471
    Prev
    Next
    INDEX
    Explanations

    hit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stated
    -0.09
     trunks
    -0.08
    hh
    -0.08
     borderline
    -0.07
     Ehren
    -0.07
     மண
    -0.07
    checkpoint
    -0.07
    HH
    -0.07
     خ
    -0.07
    regel
    -0.07
    POSITIVE LOGITS
     Norman
    0.08
     بث
    0.08
     igen
    0.08
     muri
    0.07
     согласно
    0.07
     baza
    0.07
     ож
    0.07
    率
    0.07
     frenzy
    0.07
     mas
    0.07
    Activations Density 0.010%

    No Known Activations